diff options
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/file_table.c | 14 | ||||
| -rw-r--r-- | fs/namei.c | 75 | ||||
| -rw-r--r-- | fs/open.c | 36 |
3 files changed, 113 insertions, 12 deletions
diff --git a/fs/file_table.c b/fs/file_table.c index 3f73eb1f195..71efc700022 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -199,6 +199,17 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry, file->f_mapping = dentry->d_inode->i_mapping; file->f_mode = mode; file->f_op = fop; + + /* + * These mounts don't really matter in practice + * for r/o bind mounts. They aren't userspace- + * visible. We do this for consistency, and so + * that we can do debugging checks at __fput() + */ + if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) { + error = mnt_want_write(mnt); + WARN_ON(error); + } return error; } EXPORT_SYMBOL(init_file); @@ -221,10 +232,13 @@ EXPORT_SYMBOL(fput); */ void drop_file_write_access(struct file *file) { + struct vfsmount *mnt = file->f_path.mnt; struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; put_write_access(inode); + if (!special_file(inode->i_mode)) + mnt_drop_write(mnt); } EXPORT_SYMBOL_GPL(drop_file_write_access); diff --git a/fs/namei.c b/fs/namei.c index 83c843b3fea..e179f71bfcb 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1623,8 +1623,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) return -EACCES; flag &= ~O_TRUNC; - } else if (IS_RDONLY(inode) && (acc_mode & MAY_WRITE)) - return -EROFS; + } error = vfs_permission(nd, acc_mode); if (error) @@ -1724,18 +1723,32 @@ static inline int open_to_namei_flags(int flag) return flag; } +static int open_will_write_to_fs(int flag, struct inode *inode) +{ + /* + * We'll never write to the fs underlying + * a device file. + */ + if (special_file(inode->i_mode)) + return 0; + return (flag & O_TRUNC); +} + /* - * Note that the low bits of "flag" aren't the same as in the open - * system call. See open_to_namei_flags(). + * Note that the low bits of the passed in "open_flag" + * are not the same as in the local variable "flag". See + * open_to_namei_flags() for more details. */ struct file *do_filp_open(int dfd, const char *pathname, int open_flag, int mode) { + struct file *filp; struct nameidata nd; int acc_mode, error; struct path path; struct dentry *dir; int count = 0; + int will_write; int flag = open_to_namei_flags(open_flag); acc_mode = ACC_MODE(flag); @@ -1791,17 +1804,30 @@ do_last: } if (IS_ERR(nd.intent.open.file)) { - mutex_unlock(&dir->d_inode->i_mutex); error = PTR_ERR(nd.intent.open.file); - goto exit_dput; + goto exit_mutex_unlock; } /* Negative dentry, just create the file */ if (!path.dentry->d_inode) { - error = __open_namei_create(&nd, &path, flag, mode); + /* + * This write is needed to ensure that a + * ro->rw transition does not occur between + * the time when the file is created and when + * a permanent write count is taken through + * the 'struct file' in nameidata_to_filp(). + */ + error = mnt_want_write(nd.path.mnt); if (error) + goto exit_mutex_unlock; + error = __open_namei_create(&nd, &path, flag, mode); + if (error) { + mnt_drop_write(nd.path.mnt); goto exit; - return nameidata_to_filp(&nd, open_flag); + } + filp = nameidata_to_filp(&nd, open_flag); + mnt_drop_write(nd.path.mnt); + return filp; } /* @@ -1831,11 +1857,40 @@ do_last: if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode)) goto exit; ok: + /* + * Consider: + * 1. may_open() truncates a file + * 2. a rw->ro mount transition occurs + * 3. nameidata_to_filp() fails due to + * the ro mount. + * That would be inconsistent, and should + * be avoided. Taking this mnt write here + * ensures that (2) can not occur. + */ + will_write = open_will_write_to_fs(flag, nd.path.dentry->d_inode); + if (will_write) { + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit; + } error = may_open(&nd, acc_mode, flag); - if (error) + if (error) { + if (will_write) + mnt_drop_write(nd.path.mnt); goto exit; - return nameidata_to_filp(&nd, open_flag); + } + filp = nameidata_to_filp(&nd, open_flag); + /* + * It is now safe to drop the mnt write + * because the filp has had a write taken + * on its behalf. + */ + if (will_write) + mnt_drop_write(nd.path.mnt); + return filp; +exit_mutex_unlock: + mutex_unlock(&dir->d_inode->i_mutex); exit_dput: path_put_conditional(&path, &nd); exit: diff --git a/fs/open.c b/fs/open.c index 8111947905d..e12f1701032 100644 --- a/fs/open.c +++ b/fs/open.c @@ -730,6 +730,35 @@ out: return error; } +/* + * You have to be very careful that these write + * counts get cleaned up in error cases and + * upon __fput(). This should probably never + * be called outside of __dentry_open(). + */ +static inline int __get_file_write_access(struct inode *inode, + struct vfsmount *mnt) +{ + int error; + error = get_write_access(inode); + if (error) + return error; + /* + * Do not take mount writer counts on + * special files since no writes to + * the mount itself will occur. + */ + if (!special_file(inode->i_mode)) { + /* + * Balanced in __fput() + */ + error = mnt_want_write(mnt); + if (error) + put_write_access(inode); + } + return error; +} + static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, struct file *f, int (*open)(struct inode *, struct file *)) @@ -742,7 +771,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, FMODE_PREAD | FMODE_PWRITE; inode = dentry->d_inode; if (f->f_mode & FMODE_WRITE) { - error = get_write_access(inode); + error = __get_file_write_access(inode, mnt); if (error) goto cleanup_file; } @@ -784,8 +813,11 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, cleanup_all: fops_put(f->f_op); - if (f->f_mode & FMODE_WRITE) + if (f->f_mode & FMODE_WRITE) { put_write_access(inode); + if (!special_file(inode->i_mode)) + mnt_drop_write(mnt); + } file_kill(f); f->f_path.dentry = NULL; f->f_path.mnt = NULL; |